Functions — github.com/MooreThreads/Moore-AnimateAnyone

hub / github.com/MooreThreads/Moore-AnimateAnyone / functions

Functions250 in github.com/MooreThreads/Moore-AnimateAnyone

⨍ Functions 250◇ Types & classes 51

↓ 115 callersMethodto

(self, device)

src/dwpose/__init__.py:43

↓ 18 callersMethodupdate

(self, writer, dtype=torch.float16)

src/models/mutual_self_attention.py:304

↓ 12 callersFunctiontorch_dfs

(model: torch.nn.Module)

src/models/mutual_self_attention.py:12

↓ 10 callersMethodclear

(self)

src/models/mutual_self_attention.py:343

↓ 6 callersMethod__init__

( self, in_channels: int, prev_output_channel: int, out_channels: int,

src/models/unet_2d_blocks.py:963

↓ 6 callersMethodfrom_pretrained_2d

( cls, pretrained_model_path: PathLike, motion_module_path: PathLike, subfolde

src/models/unet_3d.py:605

↓ 5 callersFunctionget_motion_module

(in_channels, motion_module_type: str, motion_module_kwargs: dict)

src/models/motion_module.py:34

↓ 5 callersFunctionread_frames

(video_path)

src/utils/util.py:106

↓ 4 callersMethod__init__

( self, in_channels: int, prev_output_channel: int, out_channels: int,

src/models/unet_3d_blocks.py:793

↓ 4 callersMethod__init__

(self, d_model, dropout=0.0, max_len=24)

src/models/motion_module.py:263

↓ 4 callersFunctionget_fps

(video_path)

src/utils/util.py:123

↓ 4 callersFunctionsave_videos_grid

(videos: torch.Tensor, path: str, rescale=False, n_rows=6, fps=8)

src/utils/util.py:86

↓ 3 callersMethodaugmentation

(self, image, transform, state=None)

src/dataset/dance_image.py:68

↓ 3 callersMethodaugmentation

(self, images, transform, state=None)

src/dataset/dance_video.py:69

↓ 3 callersFunctionsave_checkpoint

(model, save_dir, prefix, ckpt_num, total_limit=None)

train_stage_1.py:689

↓ 3 callersFunctionsave_videos_from_pil

(pil_images, path, fps=8)

src/utils/util.py:51

↓ 2 callersMethod__init__

( self, channels, use_conv=False, use_conv_transpose=False, out_channe

src/models/resnet.py:32

↓ 2 callersFunction_get_3rd_point

To calculate the affine matrix, three pairs of points are required. This function is used to get the 3rd point, given 2D points a & b. The 3r

src/dwpose/onnxpose.py:187

↓ 2 callersFunctiondelete_additional_ckpt

(base_path, num_keep)

src/utils/util.py:35

↓ 2 callersFunctionface_image

(frame, save_path=None)

tools/facetracker_api.py:12

↓ 2 callersMethodforward

(self, hidden_states)

src/models/resnet.py:251

↓ 2 callersFunctionget_context_scheduler

(name: str)

src/pipelines/context.py:45

↓ 2 callersFunctionget_down_block

( down_block_type: str, num_layers: int, in_channels: int, out_channels: int, temb_channel

src/models/unet_2d_blocks.py:20

↓ 2 callersFunctionget_tensor_interpolation_method

()

src/pipelines/utils.py:6

↓ 2 callersFunctionget_up_block

( up_block_type: str, num_layers: int, in_channels: int, out_channels: int, prev_output_ch

src/models/unet_2d_blocks.py:102

↓ 2 callersFunctionimport_filename

(filename)

src/utils/util.py:27

↓ 2 callersFunctionordered_halving

(val)

src/pipelines/context.py:7

↓ 2 callersFunctionseed_everything

(seed)

src/utils/util.py:16

↓ 2 callersFunctionzero_module

(module)

src/models/motion_module.py:15

↓ 1 callersMethod__init__

( self, dim: int, num_attention_heads: int, attention_head_dim: int, d

src/models/attention.py:47

↓ 1 callersMethod_encode_prompt

( self, prompt, device, num_videos_per_prompt, do_classifier_free_guid

src/pipelines/pipeline_lmks2vid_long.py:206

↓ 1 callersFunction_fix_aspect_ratio

Extend the scale to match the given aspect ratio. Args: scale (np.ndarray): The image scale (w, h) in shape (2, ) aspect_ratio (f

src/dwpose/onnxpose.py:153

↓ 1 callersFunction_rotate_point

Rotate a point by an angle. Args: pt (np.ndarray): 2D point coordinates (x, y) in shape (2, ) angle_rad (float): rotation angle i

src/dwpose/onnxpose.py:172

↓ 1 callersFunctionadjust_pose

(src_lms_list, src_size, ref_lms, ref_size)

scripts/lmks2vid.py:136

↓ 1 callersFunctionbatch_rearrange

(pose_len, batch_size=24)

scripts/lmks2vid.py:108

↓ 1 callersFunctionbbox_xyxy2cs

Transform the bbox format from (x,y,w,h) into (center, scale) Args: bbox (ndarray): Bounding box(es) in shape (4,) or (n, 4), formatted

src/dwpose/onnxpose.py:118

↓ 1 callersFunctioncompute_snr

Computes SNR as per https://github.com/TiankaiHang/Min-SNR-Diffusion-Training/blob/521b624bd70c67cee4bdf49225915f5945a872e3/guided_diffusion/

train_stage_2.py:106

↓ 1 callersFunctioncompute_snr

Computes SNR as per https://github.com/TiankaiHang/Min-SNR-Diffusion-Training/blob/521b624bd70c67cee4bdf49225915f5945a872e3/guided_diffusion/

train_stage_1.py:97

↓ 1 callersFunctiondecode

Modulate simcc distribution with Gaussian. Args: simcc_x (np.ndarray[K, Wx]): model predicted simcc in x. simcc_y (np.ndarray[K,

src/dwpose/onnxpose.py:342

↓ 1 callersMethoddecode_latents

(self, latents)

src/pipelines/pipeline_lmks2vid_long.py:134

↓ 1 callersMethoddecode_latents

(self, latents)

src/pipelines/pipeline_pose2vid.py:104

↓ 1 callersMethoddecode_latents

(self, latents)

src/pipelines/pipeline_pose2img.py:102

↓ 1 callersMethoddecode_latents

(self, latents)

src/pipelines/pipeline_pose2vid_long.py:112

↓ 1 callersFunctiondemo_postprocess

(outputs, img_size, p6=False)

src/dwpose/onnxdet.py:61

↓ 1 callersFunctiondraw_pose

(pose, H, W)

src/dwpose/__init__.py:22

↓ 1 callersFunctionget_simcc_maximum

Get maximum response location and value from simcc representations. Note: instance number: N num_keypoints: K heatmap hei

src/dwpose/onnxpose.py:296

↓ 1 callersFunctionget_warp_matrix

Calculate the affine transformation matrix that can warp the bbox area in the input image to the output size. Args: center (np.ndarra

src/dwpose/onnxpose.py:206

↓ 1 callersFunctioninference

Inference RTMPose model. Args: sess (ort.InferenceSession): ONNXRuntime session. img (np.ndarray): Input image in shape. Ret

src/dwpose/onnxpose.py:54

↓ 1 callersFunctioninference_detector

(session, oriImg)

src/dwpose/onnxdet.py:103

↓ 1 callersFunctioninference_pose

(session, out_bbox, oriImg)

src/dwpose/onnxpose.py:363

↓ 1 callersMethodinterpolate_latents

( self, latents: torch.Tensor, interpolation_factor: int, device )

src/pipelines/pipeline_lmks2vid_long.py:314

↓ 1 callersMethodinterpolate_latents

( self, latents: torch.Tensor, interpolation_factor: int, device )

src/pipelines/pipeline_pose2vid_long.py:292

↓ 1 callersFunctionlmks_video_extract

(video_path)

scripts/lmks2vid.py:119

↓ 1 callersFunctionlmks_vis

(img, lms)

scripts/lmks2vid.py:74

↓ 1 callersFunctionlog_validation

( vae, image_enc, net, scheduler, accelerator, width, height, clip_length=24,

train_stage_2.py:136

↓ 1 callersFunctionlog_validation

( vae, image_enc, net, scheduler, accelerator, width, height, )

train_stage_1.py:127

↓ 1 callersFunctionmain

(cfg)

train_stage_2.py:225

↓ 1 callersFunctionmain

(cfg)

train_stage_1.py:210

↓ 1 callersFunctionmain

()

scripts/lmks2vid.py:155

↓ 1 callersFunctionmain

()

scripts/pose2vid.py:42

↓ 1 callersFunctionmulticlass_nms

Multiclass NMS implemented in Numpy. Class-aware version.

src/dwpose/onnxdet.py:37

↓ 1 callersFunctionnms

Single class NMS implemented in Numpy.

src/dwpose/onnxdet.py:7

↓ 1 callersFunctionparse_args

()

scripts/lmks2vid.py:37

↓ 1 callersFunctionparse_args

()

scripts/pose2vid.py:27

↓ 1 callersFunctionpostprocess

Postprocess for RTMPose model output. Args: outputs (np.ndarray): Output of RTMPose model. model_input_size (tuple): RTMPose mode

src/dwpose/onnxpose.py:82

↓ 1 callersFunctionprepare_anyone

()

tools/download_weights.py:83

↓ 1 callersFunctionprepare_base_model

()

tools/download_weights.py:7

↓ 1 callersFunctionprepare_dwpose

()

tools/download_weights.py:41

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

src/pipelines/pipeline_lmks2vid_long.py:149

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

src/pipelines/pipeline_pose2vid.py:119

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

src/pipelines/pipeline_pose2img.py:117

↓ 1 callersMethodprepare_extra_step_kwargs

(self, generator, eta)

src/pipelines/pipeline_pose2vid_long.py:127

↓ 1 callersFunctionprepare_image_encoder

()

tools/download_weights.py:24

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_lmks2vid_long.py:170

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_pose2vid.py:140

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, dtype

src/pipelines/pipeline_pose2img.py:138

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_pose2vid_long.py:148

↓ 1 callersFunctionprepare_vae

()

tools/download_weights.py:62

↓ 1 callersFunctionpreprocess

(img, input_size, swap=(2, 0, 1))

src/dwpose/onnxdet.py:84

↓ 1 callersFunctionpreprocess

Do preprocessing for RTMPose model inference. Args: img (np.ndarray): Input image in shape. input_size (tuple): Input image size

src/dwpose/onnxpose.py:9

↓ 1 callersFunctionprocess_single_video

(video_path, detector, root_dir, save_dir)

tools/extract_dwpose_from_vid.py:15

↓ 1 callersMethodregister_reference_hooks

( self, mode, do_classifier_free_guidance, attention_auto_machine_weight,

src/models/mutual_self_attention.py:52

↓ 1 callersFunctionrescale_noise_cfg

Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and Sample Steps are Flawed](http

src/pipelines/pipeline_lmks2vid_long.py:29

↓ 1 callersFunctionsave_checkpoint

(model, save_dir, prefix, ckpt_num, total_limit=None)

train_stage_2.py:715

↓ 1 callersMethodset_attention_slice

r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to

src/models/unet_3d.py:303

↓ 1 callersMethodset_attention_slice

r""" Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to comp

src/models/unet_2d_condition.py:762

↓ 1 callersMethodset_attn_processor

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

src/models/unet_2d_condition.py:701

↓ 1 callersFunctiontop_down_affine

Get the bbox image as the model input by affine transform. Args: input_size (dict): The input size of the model. bbox_scale (dict

src/dwpose/onnxpose.py:262

↓ 1 callersFunctionui

()

app.py:153

Method__call__

( self, ref_image, pose_up_images, pose_down_images, width, h

src/pipelines/pipeline_lmks2vid_long.py:360

Method__call__

( self, ref_image, pose_images, width, height, video_length,

src/pipelines/pipeline_pose2vid.py:285

Method__call__

( self, ref_image, pose_image, width, height, num_inference_st

src/pipelines/pipeline_pose2img.py:193

Method__call__

( self, ref_image, pose_images, width, height, video_length,

src/pipelines/pipeline_pose2vid_long.py:338

Method__call__

(self, oriImg)

src/dwpose/wholebody.py:29

Method__call__

( self, input_image, detect_resolution=512, image_resolution=512, outp

src/dwpose/__init__.py:62

Method__getitem__

(self, index)

src/dataset/dance_image.py:73

Method__getitem__

(self, index)

src/dataset/dance_video.py:79

Method__init__

( self, reference_unet: UNet2DConditionModel, denoising_unet: UNet3DConditionModel,

train_stage_2.py:59

Method__init__

( self, config_path="./configs/prompts/animation.yaml", weight_dtype=torch.float16,

app.py:23

Method__init__

( self, reference_unet: UNet2DConditionModel, denoising_unet: UNet3DConditionModel,

train_stage_1.py:50

next →1–100 of 250, ranked by callers